#Three lines to make our compiler able to draw:

import sys

import matplotlib

matplotlib.use('Agg')

​

import pandas

from sklearn import tree

from sklearn.tree import DecisionTreeClassifier

import matplotlib.pyplot as plt

​

df = pandas.read_csv("data.csv")

​

d = {'UK': 0, 'USA': 1, 'N': 2}

df['Nationality'] = df['Nationality'].map(d)

d = {'YES': 1, 'NO': 0}

df['Go'] = df['Go'].map(d)

​

features = ['Age', 'Experience', 'Rank', 'Nationality']

​

X = df[features]

y = df['Go']

​

dtree = DecisionTreeClassifier()

dtree = dtree.fit(X, y)

​

tree.plot_tree(dtree, feature_names=features)

​

#Two  lines to make our compiler able to draw:

plt.savefig(sys.stdout.buffer)

sys.stdout.flush()

​

#NOTE:

#You will see that the Decision Tree gives you different results if you run it enough times, even if you feed it with the same data.

​

#That is because the Decision Tree does not give us a 100% certain answer. It is based on the probability of an outcome, and the answer will vary.

​

Age,Experience,Rank,Nationality,Go

36,10,9,UK,NO

42,12,4,USA,NO

23,4,6,N,NO

52,4,4,USA,NO

43,21,8,USA,YES

44,14,5,UK,NO

66,3,7,N,YES

35,14,9,UK,YES

52,13,7,N,YES

35,5,9,N,YES

24,3,5,USA,NO

18,3,7,UK,YES

45,9,9,UK,YES

​